arXiv research

Paper analyzes iterative learning for concept classes and learns half-spaces.

Iterative method learns unknown constraints for MPC control.

Paper tightens privacy and generalization bounds for iterative learning.

OMWU shows last iterate convergence in convex-concave games.

IDGL learns better graph structure and embeddings iteratively.

Data application developers and data scientists spend an inordinate amount of time iterating on machine learning (ML) workflows -- by modifying the data pre-processing, model training, and post-processing steps -- via trial-and-error to achieve the desired model performance. Existing work on accelerating machine learni…

We consider the problem of supervised learning with convex loss functions and propose a new form of iterative regularization based on the subgradient method. Unlike other regularization approaches, in iterative regularization no constraint or penalization is considered, and generalization is achieved by (early) stoppin…

The paper analyzes generalization of noisy iterative algorithms using communication theory.

OptEx accelerates first-order optimization with parallelized iterations.

New algorithm minimizes worst-case regret in uncertain, time-varying dynamics.

New method improves subspace iteration for eigenvectors in machine learning.

The paper challenges the belief that more inner iterations at test time improve performance in implicit deep learning.

EarlyStopping package helps prevent overfitting in iterative learning procedures.

Graph neural network executes value iteration for flexible environments.

Meta-learning control algorithm with finite-time guarantees for unknown systems.

LocalKMeans parallelizes Lloyd's algorithm for distributed data.

Last-iterate guarantees for learning in co-coercive games under noisy feedback.

This work uses QPGPs to improve ILC performance in repetitive tasks.

New approach uses hinge loss for iterative regularization in classification.

Method teaches students without teachers, estimating true labels from crowdsourcing.

Novel algorithm for Markov decision processes using rank-one approximation.

An important result from psycholinguistics (Griffiths & Kalish, 2005) states that no language can be learned iteratively by rational agents in a self-sustaining manner. We show how to modify the learning process slightly in order to achieve self-sustainability. Our work is in two parts. First, we characterize iterated …

The paper proposes an iterative approach to batch reinforcement learning for safer and more informative data collection.

In this paper, we propose an end-to-end graph learning framework, namely Deep Iterative and Adaptive Learning for Graph Neural Networks (DIAL-GNN), for jointly learning the graph structure and graph embeddings simultaneously. We first cast the graph structure learning problem as a similarity metric learning problem and…

The paper analyzes when credal sets stabilize under iterative updates in machine learning.

Deep RL agents suffer from transient non-stationarity, which ITER mitigates.

Machine learning workflow development is anecdotally regarded to be an iterative process of trial-and-error with humans-in-the-loop. However, we are not aware of quantitative evidence corroborating this popular belief. A quantitative characterization of iteration can serve as a benchmark for machine learning workflow d…

The paper bounds generalization error for iterative learning with bounded updates.

Improved ADMM for convex distributed learning with differential privacy.

Approximate dynamic programming algorithms, such as approximate value iteration, have been successfully applied to many complex reinforcement learning tasks, and a better approximate dynamic programming algorithm is expected to further extend the applicability of reinforcement learning to various tasks. In this paper w…

DSPI connects natural policy gradient to policy iteration, proving global convergence.

We propose and analyze a new type of stochastic first order method: gradient descent with compressed iterates (GDCI). GDCI in each iteration first compresses the current iterate using a lossy randomized compression technique, and subsequently takes a gradient step. This method is a distillation of a key ingredient in t…

New method learns collective variables using autoencoders for molecular simulations.

HyperImpute improves iterative imputation by automatically selecting models and hyperparameters.

XLVINs improve data efficiency in implicit planning by leveraging latent space.

Minimax optimal convergence rates for classes of stochastic convex optimization problems are well characterized, where the majority of results utilize iterate averaged stochastic gradient descent (SGD) with polynomially decaying step sizes. In contrast, SGD's final iterate behavior has received much less attention desp…

The big data trend has inspired feature-driven learning tasks, which cannot be handled by conventional machine learning models. Unstructured data produces very large binary matrices with millions of columns when converted to vector form. However, such data is often sparse, and hence can be manageable through the use of…

XLVINs improve deep reinforcement learning by combining self-supervised learning and neural algorithmic reasoning.

We adapt the optimization's concept of momentum to reinforcement learning. Seeing the state-action value functions as an analog to the gradients in optimization, we interpret momentum as an average of consecutive $q$-functions. We derive Momentum Value Iteration (MoVI), a variation of Value Iteration that incorporates …

DSVGD improves federated learning with fewer communication rounds.

Paper refutes conjecture on tensor power iteration convergence in overcomplete models.

A new iterative K-FAC algorithm reduces training time and memory usage.

Solving inverse problems with iterative algorithms is popular, especially for large data. Due to time constraints, the number of possible iterations is usually limited, potentially affecting the achievable accuracy. Given an error one is willing to tolerate, an important question is whether it is possible to modify the…

Local Linear embedding (LLE) is a popular dimension reduction method. In this paper, we first show LLE with nonnegative constraint is equivalent to the widely used Laplacian embedding. We further propose to iterate the two steps in LLE repeatedly to improve the results. Thirdly, we relax the kNN constraint of LLE and p…

Study spectral learning for odeco tensors, addressing initialization bottlenecks.

Robust reinforcement learning aims to produce policies that have strong guarantees even in the face of environments/transition models whose parameters have strong uncertainty. Existing work uses value-based methods and the usual primitive action setting. In this paper, we propose robust methods for learning temporally …

Combines deep learning and iterative methods for robust phase retrieval.

Within a statistical learning setting, we propose and study an iterative regularization algorithm for least squares defined by an incremental gradient method. In particular, we show that, if all other parameters are fixed a priori, the number of passes over the data (epochs) acts as a regularization parameter, and prov…